Update README on normalize_embeddings option

Paulooh007 · Nov 7, 2023 · 21236e1 · 21236e1
1 parent 2cc5434
commit 21236e1
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/laser_encoders/README.md b/laser_encoders/README.md
@@ -37,6 +37,9 @@ encoder = LaserEncoderPipeline(lang="igbo")
 
 # Encode sentences into embeddings
 embeddings = encoder.encode_sentences(["nnọọ, kedu ka ị mere"])
+# If you want the output embeddings to be L2-normalized, set normalize_embeddings to True
+normalized_embeddings = encoder.encode_sentences(["nnọọ, kedu ka ị mere"], normalize_embeddings=True)
+
 ```
 
 If you prefer more control over the tokenization and encoding process, you can initialize the tokenizer and encoder separately: